amd/blis
1
0
Fork 0
mirror of https://github.com/amd/blis.git synced 2026-05-13 02:25:39 +00:00
Code Issues Packages Projects Releases Wiki Activity

Added experimental bli_gemm_ker_var5().

Browse Source 
Details:
- Added support for an experimental gemm macro-kernel incrementally
  packs one micro-panel of B at a time. This is useful for certain
  special cases of gemm where m is small.
- Minor changes to default values of clarksville configuration.
- Defined BLIS_PACKED_BLOCKS as part of pack_t type, even though we
  do not yet have any use (or implementation support) for block storage.
- Comment update to bli_packm_init.c.
This commit is contained in:
Field G. Van Zee
2013-07-08 11:24:18 -05:00
parent 9915d667a7
commit 3725013985
12 changed files with 533 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
testsuite/src/test_libblis.c
View File

@@ -534,6 +534,15 @@ void libblis_test_output_params_struct( FILE* os, test_params_t* params )
BLIS_EXTEND_NR_D,
BLIS_EXTEND_NR_C,
BLIS_EXTEND_NR_Z );
/*
libblis_test_fprintf_c( os, "\n" );
libblis_test_fprintf_c( os, "level-3 incremental packing blocksizes \n" );
libblis_test_fprintf_c( os, " n dimension %5u %5u %5u %5u\n",
BLIS_DEFAULT_NI_S,
BLIS_DEFAULT_NI_D,
BLIS_DEFAULT_NI_C,
BLIS_DEFAULT_NI_Z );
*/
libblis_test_fprintf_c( os, "\n" );
libblis_test_fprintf_c( os, "level-3 packing duplication \n" );
libblis_test_fprintf_c( os, " dupl. factors for B %5u %5u %5u %5u\n",